SpikingBrain is a family of brain-inspired large language models (LLMs) developed by researchers at the Institute of Automation, Chinese Academy of Sciences. Introduced in September 2025, it mimics biological neural processes using spiking neural networks to achieve high efficiency, particularly for long-context tasks. Variants include SpikingBrain-7B (linear LLM) and SpikingBrain-76B (hybrid-linear Mixture-of-Experts LLM). It runs on Chinese hardware like MetaX C550 GPUs and is detailed in an arXiv technical report (arXiv:2509.05276).